Every time I fire a conversational designer, the performance of the dialog system goes down
This work addresses the data efficiency problem for developers of task-oriented dialogue systems, though it appears incremental as it builds on existing methods for knowledge injection.
The paper tackles the problem of reducing the need for large annotated datasets in neural-based task-oriented dialogue systems by incorporating explicit domain knowledge from conversational designers. Results show that using semi-logical rules in the proposed CLINN system significantly outperforms a state-of-the-art neural-based system on the MultiWOZ Restaurant dataset.
Incorporating explicit domain knowledge into neural-based task-oriented dialogue systems is an effective way to reduce the need of large sets of annotated dialogues. In this paper, we investigate how the use of explicit domain knowledge of conversational designers affects the performance of neural-based dialogue systems. To support this investigation, we propose the Conversational-Logic-Injection-in-Neural-Network system (CLINN) where explicit knowledge is coded in semi-logical rules. By using CLINN, we evaluated semi-logical rules produced by a team of differently skilled conversational designers. We experimented with the Restaurant topic of the MultiWOZ dataset. Results show that external knowledge is extremely important for reducing the need of annotated examples for conversational systems. In fact, rules from conversational designers used in CLINN significantly outperform a state-of-the-art neural-based dialogue system.